In the vqa_dataset.py, I don't understand when the split != 'train', self.annotation will be set to 'color_test.json'. Should we modify this name manually when we are testing 'shape' or 'texture'?
Hello! You don't need to modify the name manually; it doesn't impact the results. We've still made the change from 'color_test.json' to 'vqa_test.json'.
In the vqa_dataset.py, I don't understand when the split != 'train', self.annotation will be set to 'color_test.json'. Should we modify this name manually when we are testing 'shape' or 'texture'?![WechatIMG240](https://github.com/Karine-Huang/T2I-CompBench/assets/52683908/09c6c54a-2ab5-4434-8f97-e35bd7b0fc7c)